Nonparametric Adaptive Trajectory Tracking Control of Uncertain Euler-Lagrange Systems

In this work, we consider the adaptive trajectory tracking problem for Euler-Lagrange systems with uncertain dynamics. It is assumed that only partial knowledge about the real system dynamics is known and a Gaussian process based nonparametric adaptive control method is proposed to handle the unknown dynamic part. To reduce the computational cost of the Gaussian process regression method, an online sparse implementation is employed to enable real time performance of the robust adaptive controller. The effectiveness of the proposed control strategy is verified through a simulation example on the trajectory tracking control of a robotic manipulator.